agentmods.dev

critical-auditor

critical-auditor is a skill for Claude Code from richfrem/agent-plugins-skills. It costs 32 tokens per session (464 once invoked), scanned A, a copy of gpt55-critical-auditor, MIT.

An adversarial audit of agent extensions, instructions, specifications, and orchestration. It assumes the system may be wrong and looks for ways that safety checks, isolation, or evaluation can fail.

In plain words
What is it for?
Use it to inspect execution enforcement, partial changes, sandbox boundaries, evaluation gaps, baseline integrity, and extension isolation. It is for security and reliability reviews of systems that run coding agents.
Why use it?
It exposes bypasses and untested failure paths before they cause damage. It checks whether stopping rules, change protection, test coverage, baseline comparisons, and separation between extensions actually hold.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the agent-agentic-os plugin — 26 skills, 4 commands, 6 agents, 3 hooks shipped together

not rated 6repo yesterday A scan 32 tokens copy · 91% MIT

Good fit Use it to inspect execution enforcement, partial changes, sandbox boundaries, evaluation gaps, baseline integrity, and extension isolation. It is for security and reliability reviews of systems that run coding agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richfrem/agent-plugins-skills/critical-auditor
View source ↗ richfrem/agent-plugins-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add richfrem/agent-plugins-skills --skill critical-auditor
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

Or install agent-agentic-os, the plugin that ships this one along with the rest of its 26 skills, 4 commands, 6 agents, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for critical-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/critical-auditor/github.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/critical-auditor)
Your own site
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/critical-auditor"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/critical-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for critical-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/critical-auditor"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/critical-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 91% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00464
Opus 5 $0.00016 $0.00232
Sonnet 5 $0.00006 $0.00093
Haiku 4.5 $0.00003 $0.00046

Measured 5d ago against content hash 22dbfda7974b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

critical-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

91% identical to gpt55-critical-auditor — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/agent-agentic-os/skills/critical-auditor/SKILL.md · 91 lines

What it actually says

Purpose

This skill performs a deep, adversarial system audit designed to break:

  • runtime enforcement guarantees
  • mutation safety assumptions
  • eval coverage completeness
  • plugin isolation boundaries

This is NOT a compliance review.

This is a failure-seeking audit.

Audit Mandate

You must assume:

  • The system is incorrect until proven otherwise
  • Enforcement can be bypassed unless proven impossible
  • Evals are incomplete
  • Plugins will attempt to violate boundaries
  • Mutation logic will corrupt state unless isolated

Required Focus Areas

1. Execution Enforcement

  • Can HALT be bypassed?
  • Are there code paths where violations do not interrupt execution?
  • Are exceptions truly global?

2. Mutation Integrity

  • Can partial mutations persist?
  • Are sandbox boundaries leak-proof?
  • Can state escape temp/sandbox/?

3. Eval Authority

  • What behaviors are NOT covered by evals?
  • Can mutations exploit blind spots?
  • Can regression be reclassified as acceptable?

4. Baseline Integrity

  • Can baselines be indirectly manipulated?
  • Are diffs actually verified or just declared?

5. Plugin Isolation

  • Do any skills:
    • chain multiple actions?
    • make decisions?
    • orchestrate workflows?

6. Orchestration Leakage

  • Are there hidden multi-step flows inside skills?
  • Are sub-agents behaving like orchestrators?

7. Debt System Exploits

  • Can debt accumulate without blocking progress?
  • Can agents route around debt enforcement?

Output Requirements

For every issue:

  • ID
  • Severity (P0/P1/P2)
  • Exploit scenario (MANDATORY)
  • Exact failure path
  • Why enforcement fails
  • System impact
  • Recommended fix
  • Can agent exploit automatically? (YES/NO)

Critical Rule

If you cannot prove a guarantee is enforced:

→ It must be treated as NOT enforced

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 91 lines · 32 tokens per session scan A 22dbfda7974b

Subscribe to this mod's changes

critical-auditor is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 464 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to gpt55-critical-auditor, differing in 4 lines, and is treated as a copy.

Building agentsSecurityagent-evaluationagent-orchestrationagent-pluginsagent-skillagentic-control-planeagentic-os
Related

Other skills, from other repositories

akirule

Aki's contextual rule router — invoke BEFORE acting whenever the task touches any of - .md/.vue/.css/.tsx/.rs/.sql files; docs, plan, README, CHANGELOG; UI, component, CSS, tailwind; SEO, schema, sitemap; release, version, commit, push, deploy; DB schema, migration; Tauri; i18n, UI copy; pricing, biz; UX review…

lacvietanh/akidevrule · 137 tokens

akihelp

Introduce the whole Aki Claude Code system — installed skills, the akirule passive rule router (3 tiers), the deep-think passive/active split, and a painpoint-to-prompt table for the situations people actually hit — by reading live installed state, never a hardcoded inventory. Use when the user asks what Aki…

lacvietanh/akidevrule · 96 tokens

report

Something went wrong or made the work harder — recorded where it belongs, and if it is the skill's own defect, packaged into a file you can send.

jamillazarev/multica-ops · 32 tokens

akithink

Structured deep-thinking session between agent and human for important decisions — restate the problem, excavate the goal chain to the ultimate goal, first-principles decomposition (facts/constraints/assumptions), mandatory critique (steelman, inversion, pre-mortem), then converge into a decision record. For big /…

lacvietanh/akidevrule · 113 tokens

audit

Health and opportunities: what burns tokens, what stalls, what drifted, and what the ledger counts as waste.

jamillazarev/multica-ops · 0 tokens

quick

One job, no company: three questions, one or two agents, build then review.

jamillazarev/multica-ops · 0 tokens